Luís Caldas de Oliveira

Luís Caldas de Oliveira

Auto-generated profile, based on publicly available information

Luís Caldas de Oliveira

INESC ID Lisboa, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 August 2009 in EURASIP Journal on Advances in Signal Processing
Verified
Journal Article
Open access
PDF file
DSDárcio G. Silva
Dárcio G. Silva
LOLuís C. Oliveira
Luís C. Oliveira
MAMário Andrea
Mário Andrea
This work is focused on the evaluation of different methods to estimate the amount of jitter present in speech signals. The jitter value is a measure of the irregularity of a quasiperiodic signal and is a good indicator of the presence of pathologies in the larynx such as vocal fold nodules or a vocal fold polyp. Given the irregular nature of the speech signal, each jitter estimation algorithm relies on its own model making a direct comparison of the results very difficult. For this reason, the evaluation of the different jitter estimation methods was target on their ability to detect pathological voices. Two databases were used for this evaluation: a subset of the MEEI database and a smaller database acquired in the scope of this work. The results showed that there were significant differences in the performance of the algorithms being evaluated. Surprisingly, in the largest database the best results were not achieved with the commonly used relative jitter, measured as a percentage of the glottal cycle, but with absolute jitter values measured in microseconds. Also, the new proposed measure for jitter, LocJitt, performed in general is equal to or better than the commonly used tools of MDVP and Praat.

1 December 2012
Verified
Conference Paper
Closed access
GAGopala Krishna Anumanchipalli
Gopala Krishna Anumanchipalli
LOLuis C. Oliveira
Luis C. Oliveira
ABAlan W Black
Alan W Black
This paper presents an approach for transfer of speaker intent in speech-to-speech machine translation (S2SMT). Specifically, we describe techniques to retain the prominence patterns of the source language utterance through the translation pipeline and impose this information during speech synthesis in the target language. We first present an analysis of word focus across languages to motivate the problem of transfer. We then propose an approach for training an appropriate transfer function for intonation on a parallel speech corpus in the two languages within which the translation is carried out. We present our analysis and experiments on English↔Portuguese and English↔German language pairs and evaluate the proposed transformation techniques through objective measures.

19 October 2015 in Assistive Technology
Verified
Journal Article
Closed access
LGLuís Filipe Garcia
Luís Filipe Garcia
LOLuís Caldas de Oliveira
Luís Caldas de Oliveira
David Martins de MatosDavid Martins de Matos
David Martins de Matos
This study compared the performance of two statistical location-aware pictogram prediction mechanisms, with an all-purpose (All) pictogram prediction mechanism, having no location knowledge. The All approach had a unique language model under all locations. One of the location-aware alternatives, the location-specific (Spec) approach, made use of specific language models for pictogram prediction in each location of interest. The other location-aware approach resulted from combining the Spec and the All approaches, and was designated the mixed approach (Mix). In this approach, the language models acquired knowledge from all locations, but a higher relevance was assigned to the vocabulary from the associated location. Results from simulations showed that the Mix and Spec approaches could only outperform the baseline in a statistically significant way if pictogram users reuse more than 50% and 75% of their sentences, respectively. Under low sentence reuse conditions there were no statistically significant differences between the location-aware approaches and the All approach. Under these conditions, the Mix approach performed better than the Spec approach in a statistically significant way.

1 January 2008 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
SPSérgio Paulo
Sérgio Paulo
LOLuís C. Oliveira
Luís C. Oliveira
CMCarlos Mendes
Carlos Mendes
LFLuís Figueira
Luís Figueira
RCRenato Cassaca
Renato Cassaca
HMHelena Gorete Silva Moniz
Helena Gorete Silva Moniz

9 June 2015 in ACM Transactions on Accessible Computing
Verified
Journal Article
Open access
LGLuís Filipe Garcia
Luís Filipe Garcia
LOLuís Caldas De Oliveira
Luís Caldas De Oliveira
David Martins de MatosDavid Martins de Matos
David Martins de Matos
In recent years, some works have discussed the conception of location-aware Augmentative and Alternative Communication (AAC) systems with very positive feedback from participants. However, in most cases, complementary quantitative evaluations have not been carried out to confirm those results. To contribute to clarifying the validity of these approaches, our study quantitatively evaluated the effect of using language models with location knowledge on the efficiency of a word and sentence prediction system. Using corpora collected for three different locations (classroom, school cafeteria, home), location-specific language models were trained with sentences from each location and compared with a traditional all-purpose language model, trained on all corpora. User tests showed a modest mean improvement of 2.4% and 1.3% for Words Per Minute (WPM) and Keystroke Saving Rate (KSR), respectively, but the differences were not statistically significant. Since our text prediction system relies on the concept of sentence reuse, we ran a set of simulations with language models having different sentence knowledge levels (0%, 25%, 50%, 75%, 100%). We also introduced in the comparison a second location-aware strategy that combines the location-specific approach with the all-purpose approach (mixed approach). The mixed language models performed better under low sentence-reuse conditions (0%, 25%, 50%) with 1.0%, 1.3%, and 1.2% KSR improvements, respectively. The location-specific language models performed better under high sentence-reuse conditions (75%, 100%) with 1.7% and 1.5% KSR improvements, respectively.